Commit
•
d841dec
1
Parent(s):
499a672
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,14 +6,12 @@ metrics:
|
|
| 6 |
- perplexity
|
| 7 |
---
|
| 8 |
|
| 9 |
-
#
|
|
|
|
| 10 |
|
| 11 |
-
<!-- Provide a quick summary of what the model is/does. -->
|
| 12 |
|
| 13 |
Model Developers Ranjanunicode
|
| 14 |
|
| 15 |
-
A quantized version of Llama 2 chat hugging face that can be implemented with minimal hardware requirements.
|
| 16 |
-
|
| 17 |
Input Models input text only.
|
| 18 |
|
| 19 |
Output Models generate text only.
|
|
|
|
| 6 |
- perplexity
|
| 7 |
---
|
| 8 |
|
| 9 |
+
# Q-int4 unicode-llama-2-chat-Hf-q4-2
|
| 10 |
+
- A condensed edition of Llama 2 chat hugging face, designed for deployment with minimal hardware specifications.
|
| 11 |
|
|
|
|
| 12 |
|
| 13 |
Model Developers Ranjanunicode
|
| 14 |
|
|
|
|
|
|
|
| 15 |
Input Models input text only.
|
| 16 |
|
| 17 |
Output Models generate text only.
|